[PATCH v7 6/8] fsdax: Dedup file range to use a compare function

[Shiyang Ruan]

With dax we cannot deal with readpage() etc. So, we create a dax
comparison function which is similar with
vfs_dedupe_file_range_compare().
And introduce dax_remap_file_range_prep() for filesystem use.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
 fs/dax.c             | 72 ++++++++++++++++++++++++++++++++++++++++++++
 fs/remap_range.c     | 39 +++++++++++++++++++-----
 fs/xfs/xfs_reflink.c |  8 +++--
 include/linux/dax.h  |  8 +++++
 include/linux/fs.h   | 12 +++++---
 5 files changed, 125 insertions(+), 14 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 91ceb518f66a..74dd918cff1f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1823,3 +1823,75 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 	return dax_insert_pfn_mkwrite(vmf, pfn, order);
 }
 EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
+
+static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
+		struct iomap_iter *it_dest, bool *same)
+{
+	const struct iomap *smap = &it_src->iomap;
+	const struct iomap *dmap = &it_dest->iomap;
+	loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
+	loff_t len = min(smap->length, dmap->length);
+	void *saddr, *daddr;
+	int ret;
+
+	if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
+		*same = true;
+		return len;
+	}
+
+	if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
+		*same = false;
+		return 0;
+	}
+
+	ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
+				      &saddr, NULL);
+	if (ret < 0)
+		return -EIO;
+
+	ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
+				      &daddr, NULL);
+	if (ret < 0)
+		return -EIO;
+
+	*same = !memcmp(saddr, daddr, len);
+	if (!*same)
+		return 0;
+	return len;
+}
+
+int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+		struct inode *dest, loff_t destoff, loff_t len, bool *same,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter it_src = {
+		.inode		= src,
+		.pos		= srcoff,
+		.len		= len,
+	};
+	struct iomap_iter it_dest = {
+		.inode		= dest,
+		.pos		= destoff,
+		.len		= len,
+	};
+	int id, ret;
+
+	id = dax_read_lock();
+	while ((ret = iomap_iter2(&it_src, &it_dest, ops)) > 0) {
+		it_src.processed = it_dest.processed =
+			dax_range_compare_iter(&it_src, &it_dest, same);
+	}
+	dax_read_unlock(id);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dax_dedupe_file_range_compare);
+
+int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      loff_t *len, unsigned int remap_flags,
+			      const struct iomap_ops *ops)
+{
+	return __generic_remap_file_range_prep(file_in, pos_in, file_out,
+					       pos_out, len, remap_flags, ops);
+}
+EXPORT_SYMBOL(dax_remap_file_range_prep);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index e4a5fdd7ad7b..b68a29562902 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -14,6 +14,7 @@
 #include <linux/compat.h>
 #include <linux/mount.h>
 #include <linux/fs.h>
+#include <linux/dax.h>
 #include "internal.h"
 
 #include <linux/uaccess.h>
@@ -199,9 +200,9 @@ static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
  * Compare extents of two files to see if they are the same.
  * Caller must have locked both inodes to prevent write races.
  */
-static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
-					 struct inode *dest, loff_t destoff,
-					 loff_t len, bool *is_same)
+int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+				  struct inode *dest, loff_t destoff,
+				  loff_t len, bool *is_same)
 {
 	loff_t src_poff;
 	loff_t dest_poff;
@@ -280,6 +281,7 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 out_error:
 	return error;
 }
+EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
 
 /*
  * Check that the two inodes are eligible for cloning, the ranges make
@@ -289,9 +291,11 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
  * If there's an error, then the usual negative error code is returned.
  * Otherwise returns 0 with *len set to the request length.
  */
-int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t *len, unsigned int remap_flags)
+int
+__generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				loff_t *len, unsigned int remap_flags,
+				const struct iomap_ops *dax_read_ops)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -351,8 +355,18 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	if (remap_flags & REMAP_FILE_DEDUP) {
 		bool		is_same = false;
 
-		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
-				inode_out, pos_out, *len, &is_same);
+		if (*len == 0)
+			return 0;
+
+		if (!IS_DAX(inode_in))
+			ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+					inode_out, pos_out, *len, &is_same);
+		else if (dax_read_ops)
+			ret = dax_dedupe_file_range_compare(inode_in, pos_in,
+					inode_out, pos_out, *len, &is_same,
+					dax_read_ops);
+		else
+			return -EINVAL;
 		if (ret)
 			return ret;
 		if (!is_same)
@@ -370,6 +384,15 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 
 	return ret;
 }
+EXPORT_SYMBOL(__generic_remap_file_range_prep);
+
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t *len, unsigned int remap_flags)
+{
+	return __generic_remap_file_range_prep(file_in, pos_in, file_out,
+					       pos_out, len, remap_flags, NULL);
+}
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
 loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c256104772cb..28effe537d07 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1332,8 +1332,12 @@ xfs_reflink_remap_prep(
 	if (IS_DAX(inode_in) || IS_DAX(inode_out))
 		goto out_unlock;
 
-	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-			len, remap_flags);
+	if (!IS_DAX(inode_in))
+		ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
+				pos_out, len, remap_flags);
+	else
+		ret = dax_remap_file_range_prep(file_in, pos_in, file_out,
+				pos_out, len, remap_flags, &xfs_read_iomap_ops);
 	if (ret || *len == 0)
 		goto out_unlock;
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index c63559605369..8ecd125434ef 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -239,6 +239,14 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
 s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap,
 		const struct iomap *srcmap);
+int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+				  struct inode *dest, loff_t destoff,
+				  loff_t len, bool *is_same,
+				  const struct iomap_ops *ops);
+int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      loff_t *len, unsigned int remap_flags,
+			      const struct iomap_ops *ops);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 640574294216..3e9922aac200 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -71,6 +71,7 @@ struct fsverity_operations;
 struct fs_context;
 struct fs_parameter_spec;
 struct fileattr;
+struct iomap_ops;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -2126,10 +2127,13 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 				       struct file *file_out, loff_t pos_out,
 				       size_t len, unsigned int flags);
-extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
-					 struct file *file_out, loff_t pos_out,
-					 loff_t *count,
-					 unsigned int remap_flags);
+int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				    struct file *file_out, loff_t pos_out,
+				    loff_t *len, unsigned int remap_flags,
+				    const struct iomap_ops *dax_read_ops);
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t *count, unsigned int remap_flags);
 extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
 				  loff_t len, unsigned int remap_flags);
-- 
2.32.0